© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193617
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    кау
    0.50
    на
    0.50
     Charming
    0.49
    س
    0.49
    }$.
    0.48
     ಸುಮ
    0.48
    }$
    0.47
     ಹೀ
    0.47
    ib
    0.47
    }.$
    0.46
    POSITIVE LOGITS
    ava
    0.49
    反應
    0.45
     bridged
    0.44
     Dialog
    0.43
     manusia
    0.43
    צר
    0.43
    ندگان
    0.43
     aude
    0.43
    ستگی
    0.42
     کردن
    0.42
    Activations Density 0.000%

    No Known Activations